Data Preparation

Loading the class labels sent by Forrest

cl <- read.csv("cleft_class.csv")[-18,]
f0 <- read.csv("collman15v2_tightAnnotationsF0.csv")
sf0 <- scale(f0, center = TRUE, scale = TRUE)

loc <- read.csv("locationstest20171211.csv")
table(cl$gaba)
## 
##   0   1 
## 214  22
table(cl$postgaba)
## 
##   0   1 
## 212  24
ccol <- c('blue', 'blue', 'blue', 'red', 'red', 'red', 'black', 'black', 'black', 'green', 'green', 'green')
set.seed(1030)
L <- runAll(sf0, ccol = ccol)
L[[1]] <- mlocation(f0, ccol = ccol)
plot(L[[1]])

plot(L[[2]])

plot(L[[3]])

plot(L[[4]])

pairhex(sf0)

plot(L[[6]])

plotDend(L[[7]])

##      1     21     22 
## 0.7712 0.1314 0.0975
c1 <- L[[7]]$dat$labels$col
pairs(sf0, col = viridis(max(c1))[c1], 
      pch = 19, cex = 0.2)

stackM(L[[7]], ccol = ccol, centered = TRUE, depth = 2)

clusterMeans(L[[7]], ccol = ccol)

set.seed(1030)
h2 <- hmc(sf0, maxDepth = 2)
l2 <- h2$dat$labels$col - 1
p0 <- mclust::adjustedRandIndex(l2, cl$gaba)
perms <- foreach(i = 1:1e4, .combine = c) %dopar% {
  set.seed(i*2)
  mclust::adjustedRandIndex(sample(l2), cl$gaba)
}
tmp <- h2$dat$labels$col
pairs(h2$dat$data, 
      col = viridis(max(tmp))[tmp],
      pch = 19, cex = 0.25)

plotDend(h2)

##      1      2 
## 0.8093 0.1907
stackM(h2, depth = 2, centered = TRUE, ccol = ccol)

hist(perms, xlim = c(min(perms), p0 + 0.25*p0),
     main = "permutation test of ARI values")
abline(v = p0, col = 'red')

df1 <- data.frame(loc)
df1$gaba <- as.factor(cl$gaba)
df1$classification <- as.factor(tmp -1)

p1 <- ggplot(df1, aes(x = x, y=y,z=z, col = gaba, shape = classification)) + 
  facet_wrap(~ z, ncol = 6) +
  geom_point()

p1

same as above with interactivity

ggplotly(p1)